{ "name": "root", "gauges": { "SnowballTarget.Policy.Entropy.mean": { "value": 0.7010007500648499, "min": 0.6963306069374084, "max": 2.853206157684326, "count": 20 }, "SnowballTarget.Policy.Entropy.sum": { "value": 6662.31103515625, "min": 6662.31103515625, "max": 29125.529296875, "count": 20 }, "SnowballTarget.Step.mean": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Step.sum": { "value": 199984.0, "min": 9952.0, "max": 199984.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.mean": { "value": 12.901098251342773, "min": 0.6093838214874268, "max": 12.944343566894531, "count": 20 }, "SnowballTarget.Policy.ExtrinsicValueEstimate.sum": { "value": 2515.714111328125, "min": 118.220458984375, "max": 2640.64599609375, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.mean": { "value": 0.06376199481600649, "min": 0.062385290467372054, "max": 0.07631056215865173, "count": 20 }, "SnowballTarget.Losses.PolicyLoss.sum": { "value": 0.25504797926402595, "min": 0.24954116186948821, "max": 0.38155281079325865, "count": 20 }, "SnowballTarget.Losses.ValueLoss.mean": { "value": 0.2230356797283771, "min": 0.13082675798681984, "max": 0.30749603410561877, "count": 20 }, "SnowballTarget.Losses.ValueLoss.sum": { "value": 0.8921427189135084, "min": 0.5233070319472793, "max": 1.5374801705280938, "count": 20 }, "SnowballTarget.Policy.LearningRate.mean": { "value": 8.082097306000005e-06, "min": 8.082097306000005e-06, "max": 0.000291882002706, "count": 20 }, "SnowballTarget.Policy.LearningRate.sum": { "value": 3.232838922400002e-05, "min": 3.232838922400002e-05, "max": 0.00138516003828, "count": 20 }, "SnowballTarget.Policy.Epsilon.mean": { "value": 0.10269400000000001, "min": 0.10269400000000001, "max": 0.19729400000000002, "count": 20 }, "SnowballTarget.Policy.Epsilon.sum": { "value": 0.41077600000000003, "min": 0.41077600000000003, "max": 0.96172, "count": 20 }, "SnowballTarget.Policy.Beta.mean": { "value": 0.0001444306000000001, "min": 0.0001444306000000001, "max": 0.0048649706, "count": 20 }, "SnowballTarget.Policy.Beta.sum": { "value": 0.0005777224000000004, "min": 0.0005777224000000004, "max": 0.023089828, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.mean": { "value": 199.0, "min": 199.0, "max": 199.0, "count": 20 }, "SnowballTarget.Environment.EpisodeLength.sum": { "value": 8756.0, "min": 8756.0, "max": 10945.0, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.mean": { "value": 25.477272727272727, "min": 3.909090909090909, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Environment.CumulativeReward.sum": { "value": 1121.0, "min": 172.0, "max": 1400.0, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.mean": { "value": 25.477272727272727, "min": 3.909090909090909, "max": 25.704545454545453, "count": 20 }, "SnowballTarget.Policy.ExtrinsicReward.sum": { "value": 1121.0, "min": 172.0, "max": 1400.0, "count": 20 }, "SnowballTarget.IsTraining.mean": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 }, "SnowballTarget.IsTraining.sum": { "value": 1.0, "min": 1.0, "max": 1.0, "count": 20 } }, "metadata": { "timer_format_version": "0.1.0", "start_time_seconds": "1790113376", "python_version": "3.10.21 (main, Aug 13 2026, 09:45:30) [GCC 13.3.0]", "command_line_arguments": "/content/venv310/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget4 --no-graphics --force", "mlagents_version": "1.2.0.dev0", "mlagents_envs_version": "1.2.0.dev0", "communication_protocol_version": "1.5.0", "pytorch_version": "2.8.0+cu128", "numpy_version": "1.23.5", "end_time_seconds": "1790113826" }, "total": 449.7238378490001, "count": 1, "self": 0.4783030790003977, "children": { "run_training.setup": { "total": 0.020331276999968395, "count": 1, "self": 0.020331276999968395 }, "TrainerController.start_learning": { "total": 449.22520349299975, "count": 1, "self": 0.37488278696537236, "children": { "TrainerController._reset_env": { "total": 3.1425887800000964, "count": 1, "self": 3.1425887800000964 }, "TrainerController.advance": { "total": 445.62840426203456, "count": 18192, "self": 0.4318100950158623, "children": { "env_step": { "total": 327.84396760399613, "count": 18192, "self": 256.84545782992745, "children": { "SubprocessEnvManager._take_step": { "total": 70.77687174003768, "count": 18192, "self": 1.3224891850190943, "children": { "TorchPolicy.evaluate": { "total": 69.45438255501858, "count": 18192, "self": 69.45438255501858 } } }, "workers": { "total": 0.22163803403100246, "count": 18192, "self": 0.0, "children": { "worker_root": { "total": 447.3543019869535, "count": 18192, "is_parallel": true, "self": 221.38168244094823, "children": { "run_training.setup": { "total": 0.0, "count": 0, "is_parallel": true, "self": 0.0, "children": { "steps_from_proto": { "total": 0.004037007000079029, "count": 1, "is_parallel": true, "self": 0.0026503110011617537, "children": { "_process_rank_one_or_two_observation": { "total": 0.0013866959989172756, "count": 10, "is_parallel": true, "self": 0.0013866959989172756 } } }, "UnityEnvironment.step": { "total": 0.07016805200009912, "count": 1, "is_parallel": true, "self": 0.0006000900002618437, "children": { "UnityEnvironment._generate_step_input": { "total": 0.0004019759999209782, "count": 1, "is_parallel": true, "self": 0.0004019759999209782 }, "communicator.exchange": { "total": 0.06316976400012209, "count": 1, "is_parallel": true, "self": 0.06316976400012209 }, "steps_from_proto": { "total": 0.005996221999794216, "count": 1, "is_parallel": true, "self": 0.00040486800025973935, "children": { "_process_rank_one_or_two_observation": { "total": 0.005591353999534476, "count": 10, "is_parallel": true, "self": 0.005591353999534476 } } } } } } }, "UnityEnvironment.step": { "total": 225.97261954600526, "count": 18191, "is_parallel": true, "self": 10.275533550034197, "children": { "UnityEnvironment._generate_step_input": { "total": 5.496876679995694, "count": 18191, "is_parallel": true, "self": 5.496876679995694 }, "communicator.exchange": { "total": 172.4344704660125, "count": 18191, "is_parallel": true, "self": 172.4344704660125 }, "steps_from_proto": { "total": 37.76573884996287, "count": 18191, "is_parallel": true, "self": 6.894200905842354, "children": { "_process_rank_one_or_two_observation": { "total": 30.87153794412052, "count": 181910, "is_parallel": true, "self": 30.87153794412052 } } } } } } } } } } }, "trainer_advance": { "total": 117.35262656302257, "count": 18192, "self": 0.45304021699439545, "children": { "process_trajectory": { "total": 24.482962687028248, "count": 18192, "self": 24.096785825028746, "children": { "RLTrainer._checkpoint": { "total": 0.38617686199950185, "count": 4, "self": 0.38617686199950185 } } }, "_update_policy": { "total": 92.41662365899992, "count": 90, "self": 37.980805804015745, "children": { "TorchPPOOptimizer.update": { "total": 54.43581785498418, "count": 4587, "self": 54.43581785498418 } } } } } } }, "trainer_threads": { "total": 8.899996828404255e-07, "count": 1, "self": 8.899996828404255e-07 }, "TrainerController._save_models": { "total": 0.0793267740000374, "count": 1, "self": 0.0008027240000956226, "children": { "RLTrainer._checkpoint": { "total": 0.07852404999994178, "count": 1, "self": 0.07852404999994178 } } } } } } }